MiniCPM-V · Issues· 59 open
Open on GitHubLocally synced open issues (discussions stay on GitHub)
- #1141
[MiniCPM-o-4.5] tts_bound selects a history turn's <|tts_eos|> when current speech is truncated, yielding an empty TTS span
Updated Sep 17, 2026 - #1140
MiniCPM-V 5!
Updated Sep 9, 2026 - #1073
请问MiniCPM-o 4.5现在支持LLaMA-Factory微调吗
Updated Aug 20, 2026 - #1131
MiniCPM-o 4.5: greedy decoding degenerates (empty / repetition-loop outputs) on long multimodal prefixes (>12k tokens)
Updated Aug 10, 2026 - #1127
[vllm-omni] - Does MiniCPM-o 4.5 officially support TTS generation beyond 4,096 Talker positions?
questionUpdated Aug 3, 2026 - #1093
MiniCPM-o 4.5 技术报告细节疑问。
Updated Jul 28, 2026 - #1101
[REQUEST] - Multiuse benchmarks
questionUpdated Jul 27, 2026 - #1123
[BUG] Free API key is invalid
Updated Jul 23, 2026 - #1126
Verify evals on Papers with Code
Updated Jul 23, 2026 - #1124
[BUG] <title>minicpm-o 4.5的实时API概述链接无法打开
Updated Jul 18, 2026 - #1120
MiniCPM-o 4.5 video-only LoRA on Hugging Face Jobs: compatibility notes and workarounds
Updated Jul 15, 2026 - #1110
MiniCPM-o 4.5 全双工模式是否支持 RAG？
Updated Jun 8, 2026 - #1109
MiniCPM-V 4.6 as a VLM backbone in StarVLA for LIBERO robot manipulation
Updated Jun 5, 2026 - #1084
How to finetune audio duplex ability?
Updated Jun 3, 2026 - #1106
MiniCPM-V-4.6-Instruct 这个模型，哪里可以下载
Updated May 28, 2026